Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1690 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4978. Min Act: -0.1700

Data Index: 6456195 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4744. Min Act: -0.1700

Data Index: 1417730 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4451. Min Act: -0.1700

Data Index: 3232719 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4245. Min Act: -0.1700

Data Index: 135619 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4325. Min Act: -0.1700

Data Index: 1731041 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4053. Min Act: -0.1700

Data Index: 2623460 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3985. Min Act: -0.1700

Data Index: 4762823 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4092. Min Act: -0.1700

Data Index: 882652 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4067. Min Act: -0.1700

Data Index: 7676939 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4057. Min Act: -0.1700

Data Index: 1630703 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.4072. Min Act: -0.1700

Data Index: 3448407 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3543. Min Act: -0.1700

Data Index: 1630713 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3804. Min Act: -0.1700

Data Index: 5695263 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3591. Min Act: -0.1700

Data Index: 3829500 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3592. Min Act: -0.1700

Data Index: 5604151 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3858. Min Act: -0.1700

Data Index: 3085674 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3697. Min Act: -0.1700

Data Index: 6933983 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3266. Min Act: -0.1700

Data Index: 1182215 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3592. Min Act: -0.1700

Data Index: 4074970 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4978. Min Range: -4.4978

Max Act: 4.3336. Min Act: -0.1700

Data Index: 5804734 (Open Web Text)

Max Activating Token Index: 6